gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.
Overall
score
91%
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides specific capabilities, comprehensive trigger terms covering both technical and thematic vocabulary, explicit 'Use when...' guidance, and highly distinctive terminology that minimizes conflict risk with other skills. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations' - these are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Multi-agent orchestrator for Claude Code' with specific capabilities) AND when (explicit 'Use when...' clause with comprehensive trigger scenarios including user mentions and intent like 'wants to run multiple AI agents'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'gastown', 'gas town', 'gt commands', 'bd commands', 'convoys', 'polecats', 'crew', 'rigs', 'multi-agent coordination', 'beads', 'hooks', 'molecules', 'workflows', and various role names. Covers both technical terms and domain-specific vocabulary. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique domain-specific terminology (gastown, convoys, polecats, the witness, the mayor, etc.) that would not conflict with other skills. The gt/bd CLI references create a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong skill with excellent actionability and workflow clarity, particularly in its verification checklists and error handling guidance. The progressive disclosure is well-executed with clear references to supporting files. The main weakness is verbosity - the persona, creative freedom, and interaction style sections are longer than necessary and could be condensed without losing clarity.
Suggestions
Condense the 'Creative Freedom' section - the examples are helpful but 4 detailed examples could be reduced to 2 representative ones
Merge the 'Persona' and 'Your Identity' sections into a single, shorter section since they cover similar ground
Reduce the interaction style examples - the AskUserQuestion JSON schemas are shown 4+ times when 2 would suffice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but verbose in places - the persona section, creative freedom examples, and multiple interaction style examples could be condensed. Some sections repeat concepts (e.g., 'You run everything' is stated multiple times). However, it avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout (gt sling, bd create, gt doctor), specific JSON schemas for AskUserQuestion tool calls, and copy-paste ready examples. The command reference section and verification checklists are highly actionable. | 3 / 3 |
Workflow Clarity | Excellent workflow clarity with explicit validation checkpoints - the System Readiness Checklist has clear BLOCKER criteria, the Full Flow Verification section provides a numbered sequence with validation at each step, and error severity is categorized with specific actions. | 3 / 3 |
Progressive Disclosure | Well-structured with clear navigation to reference files (tutorial.md, setup.md, commands.md, concepts.md, troubleshooting.md). Includes grep commands for navigating large files and a clear table mapping files to use cases. SKILL.md serves as an effective overview. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (705 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 13 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.